Yes — with 5.7 GB to spare
Mistral NeMo 12B at Q4_K_M fits your GeForce RTX 5060 Ti 16 GB entirely on the GPU at 8K context, at an estimated 40 tokens per second. Past 44K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Fully on GPU
8K context
Q4_K_M · 6.9 GB
Apache 2.0
Released Jul 2024
Multilingual 12B with a 128K window, built with NVIDIA. A roleplay and fiction favourite that refuses to die.
The VRAM budget
weights 6.9 GB
Weights 6.9 GB
KV cache @ 8K 1.25 GB
Runtime overhead 0.6 GB
Free 5.7 GB of 14.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 22.7 GB | 24.6 GB | — | ~3.1 | Reference | 10.2 GB over |
| Q8_0 | 12.1 GB | 13.9 GB | 11K | 22 | −0.1% ppl | Fits |
| Q6_K | 9.3 GB | 11.2 GB | 28K | 29 | −0.4% ppl | Long context |
| Q5_K_M | 8.1 GB | 9.9 GB | 36K | 34 | −0.8% ppl | Long context |
| Q4_K_M | 6.9 GB | 8.7 GB | 44K | 40 | −1.9% ppl | Recommended |
| Q3_K_M | 5.6 GB | 7.4 GB | 52K | 49 | −5.4% ppl | Long context |
| Q2_K | 4.8 GB | 6.6 GB | 57K | 57 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.
How to run it
$ ollama pull mistral-nemo:12b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run mistral-nemo:12b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 6.9 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03There is room to go to 44K context on this card.